Driving Domain Pattern Selection With Event-Based Exclusion Areas
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle systems face challenges in managing driving domains safely due to the inability to flexibly handle various events that may obstruct driving, as they primarily rely on road surface deterioration as a criterion, making it difficult to adapt to changing conditions such as weather and environmental factors.
Innovation Solution
A driving domain management unit that includes a change pattern setting portion, a driving condition monitor portion, an exclusion domain management portion, and a distribution portion, which selects typical driving permission domains based on time-series input information, collects event-related information to determine exclusion domains, and distributes this information to vehicles to ensure safe driving by prohibiting autonomous driving in affected areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If only road surface deterioration is used as a criterion for determining exclusion domains, then the system is simple to operate, but it cannot flexibly handle various events that may obstruct driving
Solution Approach 1:
The system segments the determination of exclusion domains into multiple independent components: road surface deterioration detection, event-related information collection, and typical pattern matching. Each component processes specific types of information separately, allowing the system to handle diverse events without increasing overall complexity. The segmentation enables modular processing where each module can be independently developed and maintained.
Solution Approach 2:
The system implements a universal event determination mechanism that can handle multiple types of events (weather conditions, road conditions, environmental factors) through a single integrated framework. The event-related information collection module universally processes various information sources, and the typical pattern database stores multiple event types, allowing the system to adapt to different events without requiring separate specialized systems for each event type.
2Adaptability or versatility
If multiple conditions are considered for determining ODD, then the system can flexibly treat various events, but it becomes difficult to manage safety driving domains
Solution Approach 1:
The system performs preliminary actions by pre-storing multiple typical patterns of drivable domains and event-related information in databases before actual operation. These pre-prepared patterns include various event conditions and corresponding domain restrictions. When an event occurs, the system simply matches the current situation against these pre-stored patterns, eliminating the need for complex real-time decision-making and simplifying the management of safety driving domains.
Solution Approach 2:
The system implements a feedback mechanism where event-related information is continuously collected from multiple sources, compared against stored typical patterns, and used to dynamically adjust the determination of exclusion domains. This feedback loop allows the system to automatically adapt to changing conditions while maintaining ease of operation through automated pattern matching and domain adjustment, reducing manual intervention requirements.
Data Source
AI summary
A driving domain management unit which includes a change pattern setting portion that selects one of multiple typical patterns previously patterning drivable domains based on input information changing in time series; a driving condition monitor portion that determines an event based on collected event related information from the outside; an exclusion domain management portion that determines an exclusion domain prohibiting driving of the vehicles in preference to the driving permission domain based on position information about the event, the position information being contained in the event related information used for the determination of the event; a distribution portion that distributes, to the vehicles, the selected typical pattern and the information about the determined exclusion domain or the information based on these pieces of information; and a data storage portion that stores the multiple typical patterns and the exclusion domain information.